Reflect on Session Learnings
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
Retrieve reviewed project memory that Beacon distilled from earlier agent sessions in any harness (Claude Code, Cursor, Codex, OpenCode, and others) before starting work.
Install Beacon Memory Recall
$ npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Asymptote-Labs/agent-beacon beacon-memory-recall --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-skills/skills/beacon-memory-recall .claude/skills/beacon-memory-recall && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "beacon-memory-recall" agent skill from https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recall into .claude/skills/beacon-memory-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "beacon-memory-recall", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recallType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Asymptote-Labs/agent-beacon beacon-memory-recall --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent-skills/skills/beacon-memory-recall .agents/skills/beacon-memory-recall && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "beacon-memory-recall" agent skill from https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recall into .agents/skills/beacon-memory-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "beacon-memory-recall", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Asymptote-Labs/agent-beacon beacon-memory-recall --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent-skills/skills/beacon-memory-recall .cursor/skills/beacon-memory-recall && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "beacon-memory-recall" agent skill from https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recall into .cursor/skills/beacon-memory-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "beacon-memory-recall", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Asymptote-Labs/agent-beacon.git --path agent-skills/skills/beacon-memory-recall--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Asymptote-Labs/agent-beacon beacon-memory-recall --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent-skills/skills/beacon-memory-recall .gemini/skills/beacon-memory-recall && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "beacon-memory-recall" agent skill from https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recall into .gemini/skills/beacon-memory-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "beacon-memory-recall", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Asymptote-Labs/agent-beacon beacon-memory-recallInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent-skills/skills/beacon-memory-recall .github/skills/beacon-memory-recall && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "beacon-memory-recall" agent skill from https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recall into .github/skills/beacon-memory-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "beacon-memory-recall", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Asymptote-Labs/agent-beacon beacon-memory-recall --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent-skills/skills/beacon-memory-recall .opencode/skills/beacon-memory-recall && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "beacon-memory-recall" agent skill from https://github.com/Asymptote-Labs/agent-beacon/tree/main/agent-skills/skills/beacon-memory-recall into .opencode/skills/beacon-memory-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "beacon-memory-recall", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
beacon-memory-recall- GitHub stars
- 1.8k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 557 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Retrieve reviewed project memory that Beacon distilled from earlier agent sessions in any harness (Claude Code, Cursor, Codex, OpenCode, and others) before starting work.
- Works in 3 steps: check that Beacon is available → retrieve memory → use what you found
- Asks have we seen this before
- SKILL.md covers When to recall, Step 1: check that Beacon is…, Step 2: retrieve memory and Step 3: use what you found, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Beacon Memory Recall is an agent skill from Asymptote-Labs/agent-beacon. Retrieve reviewed project memory that Beacon distilled from earlier agent sessions in any harness (Claude Code, Cursor, Codex, OpenCode, and others) before starting work. Use at the start of a non-trivial task in a repository, when the user asks "have we seen this before", "what did we learn last time", or "how did we fix this in Cursor/Codex", or when a build, test, or deploy step fails in a way that may have a known fix.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires the Beacon CLI (beacon) on PATH with endpoint capture installed. Reads only local state and makes no network calls.
It sits in Agent Workflows, covering Agent memory. The repository describes itself as: The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu. The licence is MIT.
When your agent uses it
- Asks have we seen this before
- What did we learn last time
- How did we fix this in Cursor/Codex
- Deploy step fails in a way that may have a known fix
Example prompts
- “have we seen this before”
- “what did we learn last time”
- “how did we fix this in Cursor/Codex”
- “/beacon-memory-recall”
Requirements
- Compatibility (from SKILL.md): Requires the Beacon CLI (beacon) on PATH with endpoint capture installed. Reads only local state and makes no network calls.
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 2462839. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
docs.beacon.sh
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires the Beacon CLI (beacon) on PATH with endpoint capture installed. Reads only local state and makes no network calls.
From compatibility in the SKILL.md frontmatter.
Context cost
Beacon Memory Recall loads about 1.2k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 557 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Asymptote-Labs/agent-beacon at commit 2462839, republished under its MIT licence (© Asymptote-Labs). 557 words, ~1,205 tokens.
Download SKILL.mdSave it as
.claude/skills/beacon-memory-recall/SKILL.md (or your agent's skills folder).- name
- beacon-memory-recall
- description
- Retrieve reviewed project memory that Beacon distilled from earlier agent sessions in any harness (Claude Code, Cursor, Codex, OpenCode, and others) before starting work. Use at the start of a non-trivial task in a repository, when the user asks "have we seen this before", "what did we learn last time", or "how did we fix this in Cursor/Codex", or when a build, test, or deploy step fails in a way that may have a known fix.
- compatibility
- Requires the Beacon CLI (beacon) on PATH with endpoint capture installed. Reads only local state and makes no network calls.
- license
- MIT
- metadata.author
- asymptote-labs
- metadata.homepage
- https://docs.beacon.sh/concepts/cross-harness-memory
- metadata.version
- 0.1.0
Beacon memory recall
Beacon records what agents do across every supported harness into a local log. Through
the beacon-memory-distill workflow, a person reviews selected sessions and approves the
reusable lessons into project memory. This skill reads that memory back, so you start
the task knowing what earlier agents, in this harness or any other, already learned about
this repository.
Approved memory has been reviewed by a person. Raw traces have not. Keep the two apart in everything you say.
When to recall
- Before planning a non-trivial change in a repository you have not worked in during this session.
- When a command fails in a way that could have a known fix (flaky tests, packaging, environment setup, release steps).
- When the user asks what was learned, tried, or decided before.
Skip it for trivial edits, and recall at most once per task unless the task changes direction.
Step 1: check that Beacon is available
beacon versionIf beacon is not found, tell the user that project memory is unavailable because the
Beacon CLI is not installed, point them to https://docs.beacon.sh/get-started/overview, and
continue the task without memory. Do not install it yourself.
Step 2: retrieve memory
Prefer the Beacon MCP tools when this session has them. They are named search_memory,
get_memory, and get_memory_context, usually under a server called beacon.
- Call
get_memory_contextwithtaskset to two or three distinctive keywords from the current task (a tool name, file, error string). Terms are ANDed, so a full sentence will over-constrain the search and return nothing. Drop terms if the first attempt is empty. - Call
get_memorywith anidfrom that result when you need the full body and its evidence.
Without the MCP tools, use the CLI from inside the repository:
# Up to five memories matching the task's key terms (every term must match)
beacon memory list --json --limit 5 -q "<two or three distinctive terms>"
# Everything approved for this project, newest first
beacon memory list --limit 25
# One memory in full, with its source traces
beacon memory show <memory-id>Search terms are ANDed, so start with two or three distinctive words (a tool, a file, an
error string) and drop terms if nothing matches. --kind narrows to workflow,
correction, debugging_pattern, gotcha, or convention.
Memory is scoped to the project resolved from the current directory. Run from inside the
repository, or pass --project <path>.
Show full SKILL.md (215 more words)Show less
Step 3: use what you found
- Apply a memory only when its applicability matches the current situation. Memories are lessons from specific sessions, not project policy. If one conflicts with the user's instructions or the repository's own docs (CLAUDE.md, AGENTS.md, README), follow the user and the docs, and mention the conflict.
- When a memory changes what you do, say so in one line and cite its ID, for example:
"Using Beacon memory
memory_4f2c…: package smoke needs build-pkg.sh first." - If nothing relevant comes back, carry on. Do not report an empty result unless the user asked.
Raw history, only when asked
When the user explicitly asks what happened in an earlier session ("what did Cursor do yesterday on the release script?"), you can search raw traces:
beacon endpoint traces search "<terms>" --json --limit 10
beacon endpoint traces show <trace-id> --json --limit 200Present that as unreviewed history, never as approved memory. Traces can contain prompts,
command output, and file contents: quote only what the user needs, and never repeat
anything that looks like a credential. If the history holds a lesson worth keeping,
suggest the beacon-memory-distill workflow so a person can review it.
Boundaries
- Read-only. Never approve, reject, or edit memory from this skill.
- Never run
beacon memory evaluations runhere. That step sends trace data to an evaluator over the network and belongs tobeacon-memory-distill, where the user consents to it.
© Asymptote-Labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in agent-skills/skills/beacon-memory-recall of Asymptote-Labs/agent-beacon.
Open the folder on GitHubat commit 2462839
Compare with similar skills
Beacon Memory Recall next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Beacon Memory Recall this skillAsymptote-Labs/agent-beacon | 1.8k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Reflect on Session Learningscursor/plugins | 11k | 5 repos | ~1.2k | Automated safety check: Pass | None | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT | |
| MemPalace Memory SearchMemPalace/mempalace | 60k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Compound Learning WriterEveryInc/compound-engineering-plugin | 25k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
- Official
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
MemPalace Memory Search
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
Compound Learning Writer
EveryInc/compound-engineering-plugin
Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.
Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
More from Asymptote-Labs/agent-beacon
Beacon Memory Distill
Asymptote-Labs/agent-beacon
Turn recorded agent sessions (Beacon traces from Claude Code, Cursor, Codex, OpenCode, and other harnesses) into reviewed, reusable project memory.
Beacon Lens Create
Asymptote-Labs/agent-beacon
Create, revise, debug or validate a Beacon lens, a single HTML file that renders one agent trace as a purpose-built view (a per-file review, a cost breakdown, a timeline of risky commands, a map of…
Beacon Memory Promote
Asymptote-Labs/agent-beacon
Install approved Beacon project memory as an Agent Skill in the repository (.agents/skills/<slug/SKILL.md), so every skill-capable harness loads the lesson automatically without a memory lookup.
Self Verify Beacon In Sandbox
Asymptote-Labs/agent-beacon
Verify a Beacon change end to end by running a real Claude Code session inside a disposable Linux cloud sandbox and checking that Beacon captured what the agent actually did.
Related
Categories
Questions about Beacon Memory Recall
What does Beacon Memory Recall do?
Retrieve reviewed project memory that Beacon distilled from earlier agent sessions in any harness (Claude Code, Cursor, Codex, OpenCode, and others) before starting work. Beacon Memory Recall is an agent skill from Asymptote-Labs/agent-beacon. Retrieve reviewed project memory that Beacon distilled from earlier agent sessions in any harness (Claude Code, Cursor, Codex, OpenCode, and others) before starting work.
When should I use Beacon Memory Recall?
Beacon Memory Recall fits situations like: asks have we seen this before; what did we learn last time; how did we fix this in Cursor/Codex; deploy step fails in a way that may have a known fix.
How do I install Beacon Memory Recall in Claude Code?
Run `npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a claude-code`. Or copy the skill folder (agent-skills/skills/beacon-memory-recall in Asymptote-Labs/agent-beacon) into .claude/skills/beacon-memory-recall in your project. Claude Code loads it when a task matches its description.
How do I install Beacon Memory Recall in Codex?
Run `npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a codex`. Or copy the skill folder (agent-skills/skills/beacon-memory-recall in Asymptote-Labs/agent-beacon) into .agents/skills/beacon-memory-recall in your project. Codex loads it when a task matches its description.
Can I use Beacon Memory Recall in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Asymptote-Labs/agent-beacon --skill beacon-memory-recall -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/beacon-memory-recall, .gemini/skills/beacon-memory-recall, .github/skills/beacon-memory-recall and .opencode/skills/beacon-memory-recall in your project.
What does Beacon Memory Recall need to run?
SKILL.md names no scripts, command-line tools or credentials: Beacon Memory Recall is instructions for the agent only. Compatibility (from SKILL.md): Requires the Beacon CLI (beacon) on PATH with endpoint capture installed. Reads only local state and makes no network calls..
Does Beacon Memory Recall access the network?
SKILL.md names 1 domain. As links in the text: docs.beacon.sh. This is read from the text; nothing was executed.
Is Beacon Memory Recall safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Beacon Memory Recall use?
Beacon Memory Recall is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Beacon Memory Recall use?
About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Beacon Memory Recall?
Skills that share tags, products or a category with Beacon Memory Recall: Reflect on Session Learnings (cursor/plugins, 11k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Beads Task Memory (gastownhall/beads, 28k stars) and MemPalace Memory Search (MemPalace/mempalace, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Beacon Memory Recall?
Asymptote-Labs (a GitHub organization) maintains it in Asymptote-Labs/agent-beacon, which has 1,810 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.
Source: Asymptote-Labs/agent-beacon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.